Anthropic's Alignment Science team: "legibility" or "faithfulness" of reasoning models' Chain-of-Thought can't be trusted and models may actively hide reasoning (Emilia David/VentureBeat)

Emilia David / VentureBeat:
Anthropic's Alignment Science team: “legibility” or “faithfulness” of reasoning models' Chain-of-Thought can't be trusted and models may actively hide reasoning  —  We now live in the era of reasoning AI models where the large language model (LLM) …

from Techmeme https://ift.tt/RV6Ki81